ADS Drinks & Data: Deep Dive into Machine Learning
Date: Wednesday 18 October 2017
Location: Roeterseiland Campus UvA, Roetersstraat, Building C – Room C1.03
The ADS Meet-up offers the opportunity for researchers and business to share their knowledge and give insight on a central theme, specifically on the afternoon of Wednesday 18 October this will be on Machine Learning.
In this afternoon edition, there is also the chance to network after, with drinks and snacks provided.
Introduction & Chair by Peter Bloem ADS Researcher in Machine Learning & Knowledge Representation (VU)
16:30-17:00: Speaker 1: Zeynep Akata Assistant Professor, Informatics Institute, University of Amsterdam (UvA), Scientific Manager, Delta Lab and Senior Researcher, Max Planck Institute for Informatics, Germany will present on:
“Discovering and synthesizing novel concepts with minimal supervision”
View presentation HERE
Scaling up visual category recognition to large numbers of classes remains challenging. A promising research direction is zero-shot learning, which does not require any training data to recognize new classes, but rather relies on some form of auxiliary information describing new classes. We propose and compare different class embeddings learned automatically from unlabeled text corpora, expert annotated attributes and detailed visual descriptions. Moreover, we explore humans’ natural ability to determine distinguishing properties of unknown objects through gaze fixations. Finally, we use detailed visual descriptions to generate images from scratch and to automatically generate visual explanations that justify a classification decision.
Bio: Zeynep Akata is an Assistant Professor at the University of Amsterdam and a Senior Researcher at the Max Planck Institute for Informatics. She received a MSc degree in 2011 from RWTH Aachen and a PhD degree in 2014 from INRIA Grenoble. Her research interests include machine learning with applications to computer vision, such as zero-shot learning and multimodal deep learning with generative models that combine vision and language. She received Lise-Meitner Award for Excellent Women in Computer Science from Max Planck Society in 2014 and a DARPA grant Explainable Artificial Intelligence in 2017 in collaboration with UC Berkeley.
17:00-17:30: Speaker 2: Jie Tang Associate Professor, Knowledge Engineering Lab, Department of Computer Science and Technology, Tsinghua University, Beijing, China will present on:
“AMiner: Mining Deep Knowledge from Scientific Networks”
View presentation HERE
AMiner is the second generation of the ArnetMiner system. We focus on developing author-centric analytic and mining tools for gaining a deep understanding of the large and heterogeneous networks formed by authors, papers, venues, and knowledge concepts. One fundamental goal is how to extract and integrate semantics from different sources. We have developed algorithms to automatically extract researchers’ profiles from the Web and resolve the name ambiguity problem, and connect different professional networks. We also developed methodologies to incorporate knowledge from the Wikipedia and other sources into the system to bridge the gap between network science and the web mining research. In this talk, I will focus on answering two fundamental questions for author-centric network analysis: who is who? and who are similar to each other? The system has been in operation since 2006 and has collected more than 100,000,000 author profiles, 200,000,000 publication papers, and 7,800,000 knowledge concepts. It has been widely used for collaboration recommendation, similarity analysis, and community evolution.
Bio: Jie Tang is a (tenured) associate professor with the Department of Computer Science and Technology at Tsinghua University, and was also visiting scholar at Cornell University, Hong Kong University of Science and Technology, and Southampton University. His interests include social network analysis, data mining, and machine learning. He has published more than 200 journal/conference papers and holds 20 patents. His papers have been cited by more than 9,200 times. He served as Associate General Chair of KDD’18, PC Co-Chair of CIKM’16 and WSDM’15, Acting Editor-in-Chief of ACM TKDD, and Associate Editors of IEEE TKDE/TBD and ACM TIST. He leads the project AMiner.org for academic social network analysis and mining, which has attracted more than 8,000,000 independent IP accesses from 220 countries/regions in the world. He was honored with the UK Royal Society-Newton Advanced Fellowship Award, CCF Young Scientist Award, and NSFC Excellent Young Scholar.
17:30-18:00: Speaker 3: Peter Grünwald Professor – Universiteit Leiden, Scientific Staff Member, Group Leader Department of Machine Learning, Centrum Wiskunde & Informatica (CWI) Amsterdam will present on:
“Bayesian inference when the model is wrong”
View presentation HERE
Bayesian inference can behave badly if the model under consideration is wrong yet useful: the posterior may fail to concentrate even for large samples, leading to extreme overfitting in practice. We demonstrate this on a very simple regression problem. The problem goes away if we make the so-called learning rate small enough, which essentially amounts to making the prior more and the data less important. Standard Bayes sets the learning rate to 1, which can be too high under model misspecification. We introduce the safe Bayesian estimator, which learns the learning rate from the data.
It behaves essentially as well as standard Bayes if the model is correct but continues to achieve good rates with wrong models. We point out relations to the learning rate as it appears in gradient descent and methods for online convex optimization such as MetaGrad.
18:00-18:45: Drinks & snacks in the cafe of the D-Building Amsterdam Business School, UvA
The event will be in English and is open to all
Amsterdam Data Science (ADS) accelerates data science research by connecting, sharing and showcasing world-class technology, expertise and talent from Amsterdam on a regional, national and international level. Our research enables business and society to better gather, store, analyse and present data in order to gain valuable insights and make informed decisions.
Find out more about ADS at http://amsterdamdatascience.nl